© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11228
    Prev
    Next
    INDEX
    Explanations

    sport-related terms and phrases

    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
    1253
    +0.13
    0.4%
    906
    +0.10
    0.3%
    344
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    81
    +0.13
    0.03
    1153
    +0.10
    0.04
    940
    +0.09
    0.03
    Negative Logits
     affari
    -0.89
     milano
    -0.87
     roberto
    -0.85
     effe
    -0.85
     alberto
    -0.84
     Settembre
    -0.83
     Ottobre
    -0.81
     javier
    -0.78
     waer
    -0.78
     stefan
    -0.77
    POSITIVE LOGITS
     playoff
    0.58
     season
    0.54
     playoffs
    0.53
     wins
    0.52
     win
    0.50
     winning
    0.49
     victories
    0.49
     victory
    0.48
    Билгалдахарш
    0.48
     postseason
    0.47
    Activations Density 0.529%

    No Known Activations