© 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. 2429
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions and the justice system

    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
    +0.13
    0.4%
    1042
    +0.13
    0.4%
    227
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1858
    +0.13
    0.02
    1093
    +0.13
    0.05
    736
    +0.10
    0.05
    Negative Logits
     makro
    -0.86
     meis
    -0.83
     teras
    -0.83
     utop
    -0.81
     traktor
    -0.80
     hek
    -0.78
     ananas
    -0.78
     baum
    -0.77
     ohr
    -0.77
     blumen
    -0.77
    POSITIVE LOGITS
     identified
    0.64
     impostor
    0.60
    Identified
    0.59
     Identified
    0.58
     certitude
    0.58
     belliger
    0.56
     whom
    0.56
     Celui
    0.55
    identified
    0.55
     imposter
    0.53
    Activations Density 0.576%

    No Known Activations