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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6775
    Prev
    Next
    INDEX
    Explanations

    technical information related to system updates and software development

    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
    +0.53
    2.6%
    1577
    +0.14
    0.7%
    1967
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.53
    -0.06
    153
    +0.14
    0.05
    381
    +0.13
    0.01
    Negative Logits
    <bos>
    -1.84
    HasIndex
    -0.73
    /**
    -0.71
    <tfoot>
    -0.71
    <eos>
    -0.70
    CreateMap
    -0.67
    ///**
    -0.67
    public
    -0.65
    protected
    -0.65
    DropTable
    -0.65
    POSITIVE LOGITS
     maneu
    2.40
     accla
    2.39
     affor
    2.23
     reluct
    2.23
     shenan
    2.16
     disagre
    2.12
     increa
    2.10
     resear
    2.05
     impra
    2.04
     milf
    2.01
    Activations Density 5.753%

    No Known Activations