Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 937
    Prev
    Next
    INDEX
    Explanations

    phrases indicating assigned roles or positions

    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
    +0.29
    1.1%
    1177
    +0.11
    0.4%
    453
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1038
    +0.29
    0.05
    453
    +0.11
    0.04
    395
    +0.09
    0.03
    Negative Logits
    <bos>
    -2.41
    GraphicsUnit
    -0.63
    InputBorder
    -0.62
    IVEREF
    -0.59
    public
    -0.57
    dr
    -0.57
    //---
    -0.54
    Portale
    -0.54
    大和
    -0.54
    PBT
    -0.53
    POSITIVE LOGITS
     shenan
    1.24
     maneu
    1.21
     accla
    1.17
     chrysler
    1.14
     sappi
    1.09
     reluct
    1.09
     lidl
    1.08
     stockholm
    1.07
     hilux
    1.07
     michelin
    1.05
    Activations Density 0.325%

    No Known Activations