© 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. 3743
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings, including jury deliberations, verdicts, and court decisions

    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
    1573
    +0.10
    0.3%
    1314
    +0.09
    0.3%
    537
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1314
    +0.10
    0.03
    223
    +0.09
    0.02
    2016
    +0.09
    0.03
    Negative Logits
    ellemző
    -0.57
    Spinach
    -0.51
     trouva
    -0.49
     laurent
    -0.49
     CascadeType
    -0.49
     įsi
    -0.48
     bruno
    -0.48
    Salut
    -0.47
    Arne
    -0.47
     plomb
    -0.47
    POSITIVE LOGITS
     jury
    1.11
     Jury
    0.98
     jurors
    0.95
    Jury
    0.94
    jury
    0.90
    Jur
    0.89
     Jur
    0.87
     juries
    0.86
     juror
    0.78
     verdict
    0.63
    Activations Density 0.102%

    No Known Activations