© 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. 944
    Prev
    Next
    INDEX
    Explanations

    the word "over" or variations of it

    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
    451
    +0.07
    0.2%
    772
    +0.07
    0.2%
    1678
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    450
    +0.07
    0.03
    626
    +0.07
    0.03
    1187
    +0.07
    0.03
    Negative Logits
    (!__
    -0.89
    มาะ
    -0.74
    清
    -0.74
    addGroup
    -0.72
    GetAxis
    -0.72
    ാല
    -0.71
    ImageContext
    -0.71
    ▼
    -0.71
    ര
    -0.70
    fvar
    -0.70
    POSITIVE LOGITS
     disagre
    2.72
     ftu
    2.69
     fta
    2.68
     maneu
    2.62
     aen
    2.62
     increa
    2.60
     thut
    2.56
     excru
    2.55
     affor
    2.54
     depic
    2.51
    Activations Density 0.229%

    No Known Activations