© 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. 13207
    Prev
    Next
    INDEX
    Explanations

    phrases related to arguments or discussions

    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
    1978
    +0.12
    0.3%
    194
    +0.09
    0.3%
    453
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.12
    0.03
    981
    +0.09
    0.04
    1826
    +0.09
    0.00
    Negative Logits
     Simult
    -0.81
     indestru
    -0.76
     depic
    -0.74
     pym
    -0.74
     Rued
    -0.74
     renfer
    -0.73
     maneu
    -0.71
     luigi
    -0.69
     circums
    -0.69
     plebe
    -0.69
    POSITIVE LOGITS
    商品説明
    0.68
     SDLK
    0.53
    NOPQRST
    0.53
    SerializedSize
    0.53
     InputDecoration
    0.52
    istemas
    0.51
    "?
    0.50
     miele
    0.50
    KURZBESCHREIBUNG
    0.49
    ohist
    0.49
    Activations Density 0.315%

    No Known Activations