© 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. 10-RES-JB
    11. 3807
    Prev
    Next
    INDEX
    Explanations

    phrases indicating quantities or significant numbers

    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
    +0.33
    1.3%
    776
    +0.10
    0.4%
    1535
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    776
    +0.33
    0.08
    1265
    +0.10
    0.06
    678
    +0.10
    0.07
    Negative Logits
    <bos>
    -2.03
     intersper
    -1.25
     débats
    -1.02
     procédures
    -1.00
     déclarations
    -0.99
     modalités
    -0.97
     leçons
    -0.95
     disambigu
    -0.92
    /***
    -0.92
     négociations
    -0.91
    POSITIVE LOGITS
     palio
    1.11
     parati
    1.09
     jawa
    1.07
     particolar
    1.07
     jati
    1.06
     conflic
    1.06
     maroc
    1.05
     marea
    1.04
     cæ
    1.03
     bandung
    1.02
    Activations Density 0.734%

    No Known Activations