© 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. 13791
    Prev
    Next
    INDEX
    Explanations

    actions related to political and military strategies

    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
    1385
    +0.12
    0.4%
    1356
    +0.11
    0.3%
    1166
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    426
    +0.12
    0.04
    1356
    +0.11
    0.03
    1935
    +0.10
    0.03
    Negative Logits
     Ministre
    -0.74
     Secrétaire
    -0.63
     ibi
    -0.58
     congrès
    -0.58
     Gouvernement
    -0.57
     haer
    -0.57
     Sénat
    -0.57
    İstinadlar
    -0.56
    Przyp
    -0.56
     Traité
    -0.55
    POSITIVE LOGITS
     gains
    0.59
     gain
    0.58
    <bos>
    0.57
     foothold
    0.51
    didReceive
    0.49
     victories
    0.48
    nexpected
    0.48
    sidian
    0.47
    gain
    0.47
    endous
    0.47
    Activations Density 0.507%

    No Known Activations