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

    Neuronpedia

    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. 106
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific event or festival, specifically the "Edinburgh International Book Festival"

    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
    +0.08
    0.3%
    31
    +0.07
    0.3%
    544
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1676
    +0.08
    0.03
    969
    +0.07
    0.03
    31
    +0.07
    0.03
    Negative Logits
    <bos>
    -1.42
     endwhile
    -0.68
    sizeCache
    -0.68
    ⓧ
    -0.67
     onBind
    -0.65
    ുറ
    -0.65
     setObject
    -0.64
    setViewName
    -0.64
     وتسجيلات
    -0.63
    setClass
    -0.63
    POSITIVE LOGITS
     maneu
    1.84
     affor
    1.72
     Juf
    1.65
     Festival
    1.64
     excru
    1.62
     véhic
    1.62
     scrat
    1.59
     reluct
    1.58
     increa
    1.55
     délib
    1.54
    Activations Density 0.156%

    No Known Activations