© 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. 14887
    Prev
    Next
    INDEX
    Explanations

    titles of movies or books

    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
    1379
    +0.12
    0.4%
    61
    +0.12
    0.4%
    1325
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1379
    +0.12
    0.06
    662
    +0.12
    0.06
    1624
    +0.11
    0.05
    Negative Logits
     مرئيه
    -0.66
    ValueGenerated
    -0.65
    CopyWith
    -0.56
    OGND
    -0.54
    Tikang
    -0.53
    QMetaType
    -0.53
    ForRow
    -0.53
    awtextra
    -0.52
    principalColumn
    -0.51
    RunWith
    -0.51
    POSITIVE LOGITS
     milf
    1.43
     intersper
    1.41
     depic
    1.38
     stockholm
    1.35
     shenan
    1.34
     wikihow
    1.33
     Docteur
    1.31
     reluct
    1.31
     snoopy
    1.30
     gettyimages
    1.30
    Activations Density 0.599%

    No Known Activations