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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 602
    Prev
    Next
    INDEX
    Explanations

    references to video game characters and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.16
    1.0%
    856
    +0.11
    0.7%
    1177
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    764
    +0.16
    0.04
    227
    +0.11
    0.11
    994
    +0.07
    0.01
    Negative Logits
    <bos>
    -3.16
    IsContent
    -0.77
    SequentialGroup
    -0.74
    enumi
    -0.74
    AddTagHelper
    -0.73
    DoubleQuotes
    -0.72
    InputBorder
    -0.70
     дописавши
    -0.69
    .
    -0.68
    bibnamefont
    -0.64
    POSITIVE LOGITS
     increa
    1.75
     affor
    1.73
     impra
    1.72
     maneu
    1.70
     unwarran
    1.67
     disagre
    1.66
     emphat
    1.66
     reluct
    1.65
     inev
    1.63
     uninten
    1.63
    Activations Density 2.938%

    No Known Activations