© 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. 14827
    Prev
    Next
    INDEX
    Explanations

    verbs related to taking decisive or forceful action

    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
    683
    +0.11
    0.3%
    1526
    +0.10
    0.3%
    1839
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    683
    +0.11
    0.06
    678
    +0.10
    0.05
    1056
    +0.09
    0.05
    Negative Logits
     Rine
    -0.76
     Timp
    -0.72
     intersper
    -0.71
     Amé
    -0.69
     pymysql
    -0.69
     Incenti
    -0.69
     Daven
    -0.67
     McInt
    -0.67
     Mlle
    -0.66
     Stefanie
    -0.66
    POSITIVE LOGITS
    ing
    2.15
    ING
    1.59
    ting
    1.01
    uing
    0.93
    ging
    0.92
    ingan
    0.91
    ingi
    0.89
    ning
    0.89
    ings
    0.87
    ed
    0.85
    Activations Density 0.400%

    No Known Activations