© 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. 13858
    Prev
    Next
    INDEX
    Explanations

    alerts and warnings in text

    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
    61
    +0.15
    0.6%
    313
    +0.15
    0.5%
    596
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    61
    +0.15
    0.02
    313
    +0.15
    0.02
    1363
    +0.13
    0.02
    Negative Logits
    tomans
    -0.50
    iocene
    -0.47
     LoggerFactory
    -0.46
    fusc
    -0.46
    inoco
    -0.45
    גרפיה
    -0.45
    يميديا
    -0.45
    thier
    -0.43
    UUM
    -0.42
    rrh
    -0.42
    POSITIVE LOGITS
     alert
    1.30
     alerting
    1.19
     alerts
    1.19
     Alerts
    1.15
     Alert
    1.13
    alert
    1.08
     alerted
    1.07
    Alert
    0.99
    alerts
    0.99
     alertness
    0.97
    Activations Density 0.070%

    No Known Activations