© 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. 2393
    Prev
    Next
    INDEX
    Explanations

    sports team names or related terms

    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
    161
    +0.09
    0.3%
    1437
    +0.09
    0.3%
    553
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.09
    0.05
    1363
    +0.09
    0.05
    1120
    +0.09
    0.05
    Negative Logits
    SequentialGroup
    -0.73
    OGND
    -0.70
    webElementXpaths
    -0.69
    toluene
    -0.69
    adaptiveStyles
    -0.67
    <?
    -0.65
    Попис
    -0.64
     onPostExecute
    -0.64
    нулась
    -0.63
     хви
    -0.63
    POSITIVE LOGITS
     Cli
    2.46
    Cli
    2.23
    cli
    1.89
     cli
    1.71
     Clipper
    1.39
    CLI
    1.28
     clipper
    1.24
     CLI
    1.22
     Clifton
    1.19
     CL
    1.18
    Activations Density 0.322%

    No Known Activations