© 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. 10-RES-JB
    11. 1281
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the necessity of making choices or taking action

    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
    +0.31
    1.1%
    2000
    +0.06
    0.2%
    538
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1767
    +0.31
    0.04
    1715
    +0.06
    0.03
    550
    +0.06
    0.03
    Negative Logits
    <bos>
    -2.65
    SourceChecksum
    -0.66
    //----
    -0.61
    GIH
    -0.60
    Таким
    -0.60
    ;%%
    -0.59
    ्रिया
    -0.58
    Παραπομπές
    -0.58
    addPreferredGap
    -0.58
    <!--
    -0.58
    POSITIVE LOGITS
     hairc
    1.17
     accla
    1.16
     pamph
    1.15
     practition
    1.14
     volunte
    1.11
     véhic
    1.09
     impractica
    1.07
     maneu
    1.04
     affor
    1.04
     fortn
    1.03
    Activations Density 0.318%

    No Known Activations