© 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. 7593
    Prev
    Next
    INDEX
    Explanations

    actions and events in a sports game (specifically soccer)

    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
    +0.20
    0.6%
    736
    +0.14
    0.4%
    50
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.20
    0.09
    906
    +0.14
    -0.00
    581
    +0.10
    0.05
    Negative Logits
     milano
    -0.87
     affitto
    -0.86
     impegno
    -0.85
     accordo
    -0.83
     vacanza
    -0.82
     canel
    -0.80
     cammino
    -0.80
     appuntamento
    -0.80
     meis
    -0.80
     autunno
    -0.80
    POSITIVE LOGITS
     replays
    0.58
     replay
    0.57
     adjour
    0.55
     takeaways
    0.52
     victory
    0.52
     commendation
    0.51
     tonight
    0.51
     flashback
    0.50
     highlight
    0.50
     commentator
    0.49
    Activations Density 0.842%

    No Known Activations