© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 1660
    Prev
    Next
    INDEX
    Explanations

    ingredients commonly found in baking recipes, such as nuts and seeds

    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
    82
    +0.09
    0.3%
    347
    +0.08
    0.3%
    1339
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.09
    0.03
    1752
    +0.08
    0.03
    347
    +0.08
    0.03
    Negative Logits
    HasIndex
    -0.70
    VIAF
    -0.65
    <bos>
    -0.58
    Fordítás
    -0.58
    <!--
    -0.56
     enter
    -0.54
    Tracce
    -0.54
    //{
    -0.53
    PropertyGroup
    -0.53
     participate
    -0.52
    POSITIVE LOGITS
     nuts
    2.55
     nut
    2.43
     Nuts
    2.41
    nuts
    2.33
     Nut
    2.15
    Nut
    2.09
    nut
    2.07
    Nuts
    2.06
     NUT
    1.85
    NUT
    1.59
    Activations Density 0.200%

    No Known Activations