© 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. 13787
    Prev
    Next
    INDEX
    Explanations

    information related to legal or police-related incidents

    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
    381
    +0.15
    0.5%
    1499
    +0.14
    0.4%
    1510
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.15
    0.07
    1510
    +0.14
    0.05
    521
    +0.12
    0.04
    Negative Logits
     bordeaux
    -1.52
     matel
    -1.51
     tricot
    -1.46
     cannes
    -1.45
     swarovski
    -1.42
     murano
    -1.41
     broderie
    -1.33
     soigne
    -1.30
     chèvre
    -1.28
     marseille
    -1.28
    POSITIVE LOGITS
     said
    0.87
     noted
    0.76
     explained
    0.74
     stated
    0.74
     says
    0.73
    said
    0.73
    He
    0.72
     also
    0.70
    BeginInit
    0.70
     urged
    0.70
    Activations Density 0.244%

    No Known Activations