© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 315
    Prev
    Next
    INDEX
    Explanations

    words related to movement, specifically going up and down in various contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.10
    0.3%
    2022
    +0.07
    0.2%
    1385
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    491
    +0.10
    0.04
    1884
    +0.07
    0.04
    1317
    +0.07
    0.04
    Negative Logits
    <bos>
    -1.53
    GeneratedMessage
    -0.63
    ⓧ
    -0.62
    /*++
    -0.60
    }{||
    -0.58
    migrationBuilder
    -0.57
    setClass
    -0.56
    glBind
    -0.56
     rowspan
    -0.55
    glBindBuffer
    -0.55
    POSITIVE LOGITS
     jaya
    1.78
     lele
    1.73
     thut
    1.59
     aen
    1.57
     hcm
    1.56
     stockholm
    1.55
     meis
    1.55
     !...
    1.54
     ?...
    1.51
     „,
    1.50
    Activations Density 0.383%

    No Known Activations