© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6323
    Prev
    Next
    INDEX
    Explanations

    information related to police officers and law enforcement

    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
    658
    +0.11
    0.3%
    2042
    +0.10
    0.3%
    946
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    658
    +0.11
    0.07
    946
    +0.10
    0.06
    2042
    +0.10
    0.04
    Negative Logits
     malheur
    -0.75
     monstre
    -0.73
     oiseau
    -0.70
     créateur
    -0.69
     marchand
    -0.67
     maît
    -0.65
     pymysql
    -0.64
     bismuth
    -0.64
     génie
    -0.62
     péché
    -0.62
    POSITIVE LOGITS
     police
    0.82
     Police
    0.78
    Police
    0.66
     alkoh
    0.66
     patrolling
    0.64
     policing
    0.63
    police
    0.63
     silikon
    0.62
     patrol
    0.60
     officer
    0.59
    Activations Density 0.817%

    No Known Activations