© 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. 3608
    Prev
    Next
    INDEX
    Explanations

    violent and abusive actions or 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
    1741
    +0.17
    0.6%
    1967
    +0.16
    0.6%
    1385
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1967
    +0.17
    0.06
    1407
    +0.16
    0.05
    347
    +0.12
    0.04
    Negative Logits
    ypeł
    -0.64
     logarith
    -0.63
     zupeł
    -0.58
     $[-
    -0.58
    allclose
    -0.57
    idać
    -0.57
     keineswegs
    -0.56
     ciebie
    -0.54
     Theorems
    -0.54
    palindrome
    -0.54
    POSITIVE LOGITS
     ideolog
    0.94
     solidar
    0.94
     utop
    0.88
     vecin
    0.84
     fundament
    0.80
     hoj
    0.79
     monaster
    0.78
     robus
    0.77
     polig
    0.76
     dici
    0.76
    Activations Density 0.251%

    No Known Activations