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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 637
    Prev
    Next
    INDEX
    Explanations

    phrases related to community involvement, support, and 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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.08
    0.3%
    40
    +0.05
    0.2%
    1870
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1971
    +0.08
    0.04
    40
    +0.05
    0.03
    1133
    +0.05
    0.03
    Negative Logits
    <bos>
    -1.56
    public
    -0.85
    void
    -0.72
    class
    -0.71
    const
    -0.71
    var
    -0.71
    setClass
    -0.70
    private
    -0.70
    set
    -0.69
    //
    -0.69
    POSITIVE LOGITS
     jaya
    1.82
     stockholm
    1.71
     unwarran
    1.69
     hcm
    1.68
     unce
    1.67
     madonna
    1.67
     lamborghini
    1.66
     maroc
    1.66
     bandung
    1.65
     bordeaux
    1.63
    Activations Density 0.150%

    No Known Activations