© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 1922
    Prev
    Next
    INDEX
    Explanations

    the concept of a foundational idea or argument in discourse

    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
    528
    +0.22
    1.1%
    1983
    +0.14
    0.7%
    411
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    528
    +0.22
    0.03
    1363
    +0.14
    0.03
    1870
    +0.13
    0.02
    Negative Logits
    <bos>
    -1.58
     intersper
    -0.66
     ajudá
    -0.63
     fontaine
    -0.63
     negoti
    -0.63
     nõ
    -0.60
     Décembre
    -0.60
    daos
    -0.59
     olha
    -0.58
     Octobre
    -0.58
    POSITIVE LOGITS
     friable
    0.96
    premise
    0.94
     premise
    0.92
     premises
    0.87
    premises
    0.82
     elena
    0.81
     jessica
    0.80
     Premises
    0.79
     greyish
    0.78
     blackpink
    0.75
    Activations Density 0.186%

    No Known Activations