© 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
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 6009
    Prev
    Next
    INDEX
    Explanations

    contexts related to academic publications and research, specifically mentioning page numbers

    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
    331
    +0.16
    0.7%
    1325
    +0.14
    0.6%
    1810
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.16
    0.04
    568
    +0.14
    0.03
    1691
    +0.14
    0.03
    Negative Logits
    <bos>
    -1.36
    OGND
    -0.65
     незавершена
    -0.64
    intios
    -0.60
     bezeichneter
    -0.59
    Abitanti
    -0.59
    Климат
    -0.57
    はじめに
    -0.57
    Nationale
    -0.56
    Zdroje
    -0.56
    POSITIVE LOGITS
     pp
    1.29
     fortn
    1.24
     volunte
    1.21
     reluct
    1.20
     tolerably
    1.20
     sappi
    1.18
     impra
    1.17
     fep
    1.16
     maneu
    1.16
     fuf
    1.13
    Activations Density 0.328%

    No Known Activations