© 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. 1238
    Prev
    Next
    INDEX
    Explanations

    terms related to the effectiveness of a product or method

    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
    1994
    +0.08
    0.2%
    621
    +0.08
    0.2%
    1974
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.08
    0.04
    184
    +0.08
    0.02
    1343
    +0.07
    0.05
    Negative Logits
    FontOfSize
    -0.67
    blue
    -0.64
     Blue
    -0.64
     esta
    -0.64
     blue
    -0.62
    אר
    -0.62
    Blue
    -0.61
                                   
    -0.61
    ตลอด
    -0.60
    fre
    -0.59
    POSITIVE LOGITS
     guarante
    1.70
     wien
    1.70
     affor
    1.69
     Mlle
    1.68
     perfet
    1.65
     effe
    1.63
     increa
    1.62
     vhs
    1.61
     riviera
    1.58
     stockholm
    1.58
    Activations Density 0.444%

    No Known Activations