© 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. 13438
    Prev
    Next
    INDEX
    Explanations

    news-related information such as breaking news updates, statements from public figures, and detailed accounts of events

    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
    752
    +0.12
    0.4%
    1177
    +0.10
    0.3%
    394
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.12
    0.06
    16
    +0.10
    0.08
    897
    +0.10
    0.05
    Negative Logits
    .
    -0.82
    ,
    -0.75
    ;
    -0.74
     are
    -0.72
    /
    -0.72
    ...
    -0.71
    、
    -0.70
    ↵↵
    -0.69
     and
    -0.69
    。
    -0.68
    POSITIVE LOGITS
     Mlle
    1.57
     emphat
    1.56
     vété
    1.55
     dovr
    1.53
     increa
    1.52
     affor
    1.52
     sappi
    1.52
     hentai
    1.51
     milf
    1.51
     unlaw
    1.50
    Activations Density 0.614%

    No Known Activations