© 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. 13880
    Prev
    Next
    INDEX
    Explanations

    deadlines or time-sensitive words and phrases

    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
    1602
    +0.14
    0.5%
    1870
    +0.14
    0.5%
    1271
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1705
    +0.14
    0.04
    1363
    +0.14
    0.03
    1602
    +0.13
    0.03
    Negative Logits
     intersper
    -0.82
     compréhen
    -0.76
     confé
    -0.74
     pixabay
    -0.69
     Molto
    -0.69
     shenan
    -0.68
     accla
    -0.67
     expéri
    -0.67
     Châ
    -0.67
    Molto
    -0.66
    POSITIVE LOGITS
     criteria
    0.73
     threshold
    0.72
     criterion
    0.63
     deadline
    0.61
     thresholds
    0.61
    threshold
    0.61
     guidelines
    0.59
    ITERIA
    0.57
    Criteria
    0.57
    criteria
    0.56
    Activations Density 0.207%

    No Known Activations