© 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. 2983
    Prev
    Next
    INDEX
    Explanations

    situations and phrases indicating presence or location

    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
    +0.19
    0.8%
    197
    +0.10
    0.4%
    204
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    197
    +0.19
    0.03
    1356
    +0.10
    0.03
    1183
    +0.09
    0.03
    Negative Logits
    <bos>
    -1.81
     endeavoured
    -0.61
     strode
    -0.59
    /*++
    -0.59
     strove
    -0.58
    /***
    -0.56
     endow
    -0.56
     getNombre
    -0.56
     endeavored
    -0.56
     strolled
    -0.55
    POSITIVE LOGITS
    ouret
    0.79
     dégust
    0.78
    ereka
    0.78
     véhic
    0.77
    dison
    0.72
    antastic
    0.71
    azaki
    0.70
    ughter
    0.70
     mélang
    0.69
     proprement
    0.69
    Activations Density 0.120%

    No Known Activations