© 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. 2330
    Prev
    Next
    INDEX
    Explanations

    phrases describing permissions or prohibitions

    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
    2036
    +0.09
    0.3%
    544
    +0.09
    0.3%
    298
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1892
    +0.09
    0.03
    544
    +0.09
    0.03
    420
    +0.09
    0.03
    Negative Logits
    AutoScaleMode
    -0.64
     ideolog
    -0.64
     solidar
    -0.59
     tomat
    -0.57
     kram
    -0.56
     katal
    -0.56
     robus
    -0.55
     minimalis
    -0.55
     Wikispecies
    -0.54
     dras
    -0.54
    POSITIVE LOGITS
     Allowed
    0.77
     Forbidden
    0.72
     Plotting
    0.71
     allowed
    0.70
     simpsons
    0.65
     permitted
    0.64
    Allowed
    0.64
     Docteur
    0.63
    allowed
    0.61
     AppBundle
    0.61
    Activations Density 0.144%

    No Known Activations