Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 70
    Prev
    Next
    INDEX
    Explanations

    locations or events where different activities are happening

    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
    +0.24
    1.2%
    866
    +0.11
    0.5%
    1671
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    25
    +0.24
    0.03
    663
    +0.11
    0.02
    156
    +0.10
    0.02
    Negative Logits
    <bos>
    -3.08
    var
    -0.75
    public
    -0.74
    ByVersion
    -0.72
    rungsseite
    -0.71
    long
    -0.70
    if
    -0.70
     typelib
    -0.69
    //
    -0.68
    /**
    -0.68
    POSITIVE LOGITS
     disagre
    2.23
     affor
    2.19
     milf
    2.17
     maneu
    2.16
     ftu
    2.15
     reluct
    2.13
     fortn
    2.12
     strick
    2.10
     excru
    2.06
     increa
    2.06
    Activations Density 0.178%

    No Known Activations