© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 3799
    Prev
    Next
    INDEX
    Explanations

    statements regarding traffic rules and roadway etiquette

    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
    906
    +0.12
    0.3%
    964
    +0.11
    0.3%
    1553
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    166
    +0.12
    0.03
    946
    +0.11
    0.04
    1553
    +0.10
    0.04
    Negative Logits
     accla
    -1.12
     volunte
    -1.11
     disgra
    -1.10
     pessi
    -1.08
     Cfr
    -1.03
     embra
    -1.02
     LXXX
    -1.02
     Souha
    -1.01
     reluct
    -1.00
     tramont
    -1.00
    POSITIVE LOGITS
     traffic
    0.71
     pedestrians
    0.66
     lane
    0.62
     slow
    0.60
     lanes
    0.58
     pedestrian
    0.58
     stop
    0.54
     slowed
    0.53
     parking
    0.53
     slower
    0.53
    Activations Density 0.234%

    No Known Activations