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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3614
    Prev
    Next
    INDEX
    Explanations

    political and governmental terms and controversies

    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
    674
    +0.36
    1.5%
    1842
    +0.32
    1.3%
    609
    +0.17
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.36
    0.02
    1842
    +0.32
    0.04
    453
    +0.17
    0.05
    Negative Logits
     unspeak
    -1.12
     Considerable
    -1.08
     Whence
    -1.07
     tolerably
    -0.99
     gaily
    -0.99
     cushi
    -0.98
     unlaw
    -0.97
     ineffec
    -0.94
     tupperware
    -0.93
     indescri
    -0.93
    POSITIVE LOGITS
    <bos>
    1.30
     springfox
    0.79
     Bourgoin
    0.71
    rrggbb
    0.70
    FunctionFlags
    0.69
     ModelExpression
    0.69
     שוליים
    0.69
    IsContent
    0.68
    Erreferentziak
    0.67
     Walkover
    0.67
    Activations Density 0.417%

    No Known Activations