© 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. 13394
    Prev
    Next
    INDEX
    Explanations

    words related to legal proceedings such as court cases and charges

    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
    1343
    +0.27
    0.9%
    394
    +0.12
    0.4%
    304
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.27
    0.08
    1343
    +0.12
    0.07
    227
    +0.11
    0.06
    Negative Logits
     
    -0.88
     in
    -0.85
     no
    -0.81
    .
    -0.81
     a
    -0.81
     to
    -0.81
    ,
    -0.80
     e
    -0.79
     de
    -0.79
     non
    -0.79
    POSITIVE LOGITS
     alkoh
    2.25
     kask
    2.07
     karton
    2.06
     milano
    2.02
     marte
    2.02
     cannes
    2.01
     silikon
    1.99
     kosme
    1.98
     drap
    1.97
     moza
    1.96
    Activations Density 0.229%

    No Known Activations