© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 4778
    Prev
    Next
    INDEX
    Explanations

    webpage content related to instructions, questions, and technical specifications, particularly focused on warranties, product details, and user queries

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.17
    0.8%
    1978
    +0.12
    0.5%
    1438
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1438
    +0.17
    0.11
    908
    +0.12
    0.08
    1385
    +0.11
    0.15
    Negative Logits
    <bos>
    -4.36
    GEBURTSDATUM
    -1.29
     AssemblyCompany
    -1.27
    Autoritní
    -1.27
     autorytatywna
    -1.24
    StoreMessageInfo
    -1.16
    Билгалдахарш
    -1.13
     &___
    -1.10
    SharedDtor
    -1.09
     Administrativna
    -1.08
    POSITIVE LOGITS
     disgra
    1.26
     unlaw
    1.22
     unspeak
    1.19
     disagre
    1.19
     increa
    1.18
     impra
    1.17
     affor
    1.15
     sergio
    1.11
     apprehen
    1.10
     Manufact
    1.09
    Activations Density 2.363%

    No Known Activations