© 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. 7646
    Prev
    Next
    INDEX
    Explanations

    instances related to card games and countdowns

    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
    453
    +0.17
    0.5%
    1577
    +0.16
    0.5%
    184
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.17
    0.04
    1786
    +0.16
    0.01
    1417
    +0.16
    0.02
    Negative Logits
     wien
    -1.45
     fta
    -1.44
     „,
    -1.42
     ftu
    -1.40
     fep
    -1.37
     fte
    -1.37
     desir
    -1.37
     hcm
    -1.36
     thut
    -1.35
     dises
    -1.34
    POSITIVE LOGITS
    EndInit
    0.53
      
    0.53
     again
    0.52
    こちらも
    0.52
    <eos>
    0.51
     here
    0.50
    UnusedPrivate
    0.49
    同样
    0.49
    ).
    0.49
     per
    0.49
    Activations Density 0.113%

    No Known Activations