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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 7061
    Prev
    Next
    INDEX
    Explanations

    mentions or descriptions of specific projects, completion status, and individuals involved in construction or medical projects

    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
    1967
    +0.37
    1.7%
    1343
    +0.27
    1.2%
    184
    +0.18
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.37
    0.19
    1978
    +0.27
    0.15
    304
    +0.18
    -0.04
    Negative Logits
    <bos>
    -3.27
    Autoritní
    -1.37
     Мексичка
    -1.25
     autorytatywna
    -1.24
    Personendaten
    -1.23
     ویکی‌پدی
    -1.20
     bezeichneter
    -1.20
     Roskov
    -1.18
    GEBURTSDATUM
    -1.18
     kasarigan
    -1.16
    POSITIVE LOGITS
     meis
    1.14
     marte
    1.12
     kaos
    1.10
     moza
    1.09
     alkoh
    1.08
     inder
    1.07
     Amerik
    1.06
     boks
    1.06
     idr
    1.05
     kase
    1.05
    Activations Density 2.353%

    No Known Activations