© 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. 3854
    Prev
    Next
    INDEX
    Explanations

    mentions of legal actions such as charging, arresting, and diagnosing

    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
    1177
    +0.10
    0.3%
    1013
    +0.09
    0.3%
    1356
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1652
    +0.10
    0.05
    1056
    +0.09
    0.06
    1553
    +0.09
    0.06
    Negative Logits
     kram
    -1.29
     solidar
    -1.25
     utop
    -1.18
     ù
    -1.14
     ideolog
    -1.11
     robus
    -1.09
     doman
    -1.09
     paus
    -1.08
     uhr
    -1.07
     thuy
    -1.07
    POSITIVE LOGITS
     by
    0.69
     as
    0.59
     horned
    0.58
    ıştı
    0.55
     tört
    0.55
     sœurs
    0.53
     for
    0.53
     to
    0.52
     steamboat
    0.52
     recursively
    0.51
    Activations Density 0.358%

    No Known Activations