© 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. 7581
    Prev
    Next
    INDEX
    Explanations

    mentions of negative social behaviors or conflict situations, such as bullying or government control

    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
    752
    +0.21
    0.7%
    1967
    +0.15
    0.5%
    50
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.21
    0.07
    16
    +0.15
    0.06
    1967
    +0.10
    0.05
    Negative Logits
     ftre
    -0.74
     caufe
    -0.63
     difp
    -0.61
     fupp
    -0.60
     !...
    -0.60
     człowie
    -0.59
     garçons
    -0.59
    ;;)
    -0.59
     vnder
    -0.58
     thut
    -0.58
    POSITIVE LOGITS
    (;;)
    0.63
     Mejía
    0.62
     Cár
    0.61
     McLaugh
    0.59
     Domínguez
    0.57
     Osorio
    0.57
     Méndez
    0.57
     Marín
    0.57
     Ríos
    0.56
     Bahía
    0.56
    Activations Density 0.333%

    No Known Activations