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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 1565
    Prev
    Next
    INDEX
    Explanations

    instructions or steps for mixing or applying a substance

    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
    889
    +0.12
    0.4%
    61
    +0.09
    0.3%
    228
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    889
    +0.12
    0.03
    1950
    +0.09
    0.03
    61
    +0.09
    0.03
    Negative Logits
    <bos>
    -1.00
    public
    -0.73
    int
    -0.65
    ret
    -0.63
    private
    -0.62
    param
    -0.61
    var
    -0.60
    β
    -0.60
    const
    -0.60
    void
    -0.60
    POSITIVE LOGITS
     shake
    2.48
     shakes
    2.21
     shaking
    2.19
     Shake
    2.15
    shake
    2.03
    Shake
    1.91
     shook
    1.90
     shaken
    1.87
    shaking
    1.71
    shakes
    1.69
    Activations Density 0.166%

    No Known Activations