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

    Neuronpedia

    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. 13387
    Prev
    Next
    INDEX
    Explanations

    names of individuals involved in legal cases or criminal activities

    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
    1150
    +0.15
    0.5%
    1177
    +0.14
    0.4%
    227
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.15
    0.11
    1097
    +0.14
    0.09
    227
    +0.13
    0.09
    Negative Logits
     հղումներ
    -0.64
    GraphicsUnit
    -0.61
     ")");
    -0.61
    uxxxx
    -0.56
    AndEndTag
    -0.56
    éramos
    -0.54
    ('-'
    -0.54
    PerformLayout
    -0.53
    endpush
    -0.53
    @[+][
    -0.52
    POSITIVE LOGITS
     maneu
    1.22
     snoopy
    1.16
     depic
    1.14
     apprehen
    1.13
     disreg
    1.10
     shenan
    1.07
     budapest
    1.06
     boop
    1.06
     napoli
    1.05
     accla
    1.05
    Activations Density 0.339%

    No Known Activations