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. 6177
    Prev
    Next
    INDEX
    Explanations

    persistent URLs and links

    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
    0.9%
    1150
    +0.12
    0.5%
    1491
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    131
    +0.24
    0.04
    1150
    +0.12
    0.03
    1995
    +0.08
    0.04
    Negative Logits
    <bos>
    -2.87
    /*
    -0.88
    /**
    -0.85
    ⓧ
    -0.81
    ɵɵ
    -0.75
    Література
    -0.74
    <?
    -0.70
    /*++
    -0.68
    addGroup
    -0.68
    PerformLayout
    -0.66
    POSITIVE LOGITS
     reluct
    1.91
     maneu
    1.85
     affor
    1.83
     impra
    1.78
     disagre
    1.77
     accla
    1.76
     unlaw
    1.73
     increa
    1.71
     volunte
    1.70
     philanth
    1.68
    Activations Density 0.331%

    No Known Activations