© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2205
    Prev
    Next
    INDEX
    Explanations

    descriptors related to visual capabilities

    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
    +0.24
    0.9%
    906
    +0.13
    0.5%
    1842
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    394
    +0.24
    0.05
    1385
    +0.13
    0.06
    1839
    +0.12
    0.04
    Negative Logits
    <bos>
    -2.24
    ⓧ
    -0.65
    /*++
    -0.63
    <?
    -0.61
    FormTagHelper
    -0.56
    PutMapping
    -0.55
    SourceChecksum
    -0.55
    migrationBuilder
    -0.55
     defray
    -0.54
    Enllaços
    -0.53
    POSITIVE LOGITS
     pymysql
    0.99
     pylab
    0.93
     broderie
    0.89
     bandung
    0.84
     tucson
    0.83
     heapq
    0.83
     smtplib
    0.81
     malheure
    0.78
     swarovski
    0.78
     chré
    0.76
    Activations Density 0.668%

    No Known Activations