© 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. 13931
    Prev
    Next
    INDEX
    Explanations

    information about a versatile defensive player in football who has played multiple positions

    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
    964
    +0.09
    0.3%
    1842
    +0.08
    0.2%
    1108
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.09
    0.03
    195
    +0.08
    0.04
    736
    +0.08
    0.04
    Negative Logits
     dises
    -1.29
     sovere
    -1.29
     Juf
    -1.29
     affez
    -1.22
     fup
    -1.21
     fep
    -1.20
     fta
    -1.18
     mef
    -1.18
     seiz
    -1.17
     aen
    -1.17
    POSITIVE LOGITS
     versatility
    0.70
     role
    0.70
     versatile
    0.63
     roles
    0.62
     position
    0.60
     ролях
    0.57
     slot
    0.55
     switch
    0.54
     роль
    0.54
     play
    0.53
    Activations Density 0.295%

    No Known Activations