© 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. 2373
    Prev
    Next
    INDEX
    Explanations

    references to science fiction content

    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
    501
    +0.08
    0.2%
    2030
    +0.07
    0.2%
    395
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.08
    0.03
    144
    +0.07
    0.02
    501
    +0.06
    0.02
    Negative Logits
    <bos>
    -0.68
     continue
    -0.62
    Economía
    -0.62
     under
    -0.60
     provide
    -0.59
     even
    -0.59
    тарь
    -0.59
     unter
    -0.58
     was
    -0.58
     on
    -0.57
    POSITIVE LOGITS
    fi
    2.34
     Fi
    1.94
     fi
    1.90
    Fi
    1.81
     maneu
    1.79
     increa
    1.76
     stockholm
    1.74
    FI
    1.68
     affor
    1.67
     accla
    1.65
    Activations Density 0.217%

    No Known Activations