© 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. 13815
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports events and game progress

    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
    1081
    +0.11
    0.3%
    1252
    +0.09
    0.3%
    581
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1081
    +0.11
    0.07
    254
    +0.09
    0.05
    270
    +0.08
    0.04
    Negative Logits
     tinte
    -0.98
     utop
    -0.97
     migli
    -0.93
     solidar
    -0.93
     apparti
    -0.92
     palio
    -0.90
     ideolog
    -0.89
     elek
    -0.87
     Ottobre
    -0.87
     impon
    -0.85
    POSITIVE LOGITS
     unspeak
    0.82
     shenan
    0.78
     vainly
    0.76
     impelled
    0.76
     unve
    0.72
     ineffec
    0.71
     of
    0.71
     apprehen
    0.69
     roused
    0.68
     unavoid
    0.68
    Activations Density 0.338%

    No Known Activations