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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 12318
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically related to popular culture, politics, and technology

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1842
    +0.14
    0.4%
    198
    +0.10
    0.3%
    1741
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.14
    0.07
    1177
    +0.10
    0.04
    283
    +0.10
    0.01
    Negative Logits
     at
    -0.76
     in
    -0.72
    .
    -0.72
     as
    -0.71
    <bos>
    -0.71
    。
    -0.71
    ।
    -0.71
    …
    -0.70
     no
    -0.70
     is
    -0.69
    POSITIVE LOGITS
     pessi
    2.21
     igno
    2.15
     mef
    2.08
     hcm
    2.06
     embra
    2.06
     wien
    2.03
     emphat
    2.03
     effe
    2.02
     immen
    2.02
     suspic
    2.02
    Activations Density 0.545%

    No Known Activations