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

    Neuronpedia

    Jacobian LensNEW
    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. 11697
    Prev
    Next
    INDEX
    Explanations

    verbs related to problem-solving or accomplishment

    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
    2006
    +0.08
    0.2%
    1535
    +0.07
    0.2%
    872
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    584
    +0.08
    0.04
    100
    +0.07
    0.04
    1340
    +0.07
    0.05
    Negative Logits
    <_>
    -0.65
    amsmath
    -0.56
     "..\..\..\
    -0.55
    Jeografia
    -0.55
    Πηγή
    -0.54
    Δείτε
    -0.49
    dirent
    -0.48
    IsOptional
    -0.48
     Infatti
    -0.48
    /***
    -0.47
    POSITIVE LOGITS
     these
    0.81
     this
    0.79
     bookId
    0.73
     such
    0.72
     createDate
    0.70
    these
    0.69
     barbacoa
    0.67
     trist
    0.67
     isso
    0.65
     THESE
    0.63
    Activations Density 0.486%

    No Known Activations