© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11979
    Prev
    Next
    INDEX
    Explanations

    event details and scheduling information

    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
    1403
    +0.11
    0.3%
    2034
    +0.10
    0.3%
    678
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    109
    +0.11
    0.04
    1867
    +0.10
    0.03
    939
    +0.10
    0.05
    Negative Logits
     numberWith
    -0.63
    ControllerAdvice
    -0.61
    ਿਆ
    -0.60
    initializeApp
    -0.60
     huesos
    -0.58
    minlength
    -0.57
    )=-\
    -0.55
     =-\
    -0.54
    ictwo
    -0.53
    hasError
    -0.53
    POSITIVE LOGITS
     reluct
    1.67
     depic
    1.62
     impra
    1.59
     maneu
    1.59
     shenan
    1.53
     intersper
    1.52
     encomp
    1.52
     affor
    1.52
     fortn
    1.50
     increa
    1.49
    Activations Density 0.540%

    No Known Activations