© 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. 1021
    Prev
    Next
    INDEX
    Explanations

    information related to achievements and historical records in sports

    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
    674
    +0.10
    0.3%
    838
    +0.08
    0.2%
    1249
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1249
    +0.10
    0.03
    838
    +0.08
    0.04
    362
    +0.08
    0.04
    Negative Logits
     juf
    -0.74
     laft
    -0.67
     foon
    -0.63
     ftre
    -0.62
     reft
    -0.61
    NameValuePair
    -0.59
     beft
    -0.58
     ftu
    -0.58
    IntoConstraints
    -0.57
     feen
    -0.57
    POSITIVE LOGITS
     history
    0.58
     annals
    0.57
     ever
    0.54
    muñ
    0.53
     Tú
    0.53
     youngest
    0.50
    bánh
    0.49
     record
    0.49
    ñor
    0.49
    thage
    0.48
    Activations Density 0.175%

    No Known Activations