© 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. 4559
    Prev
    Next
    INDEX
    Explanations

    references to popular characters and franchises in entertainment

    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
    1978
    +0.16
    0.5%
    1967
    +0.14
    0.5%
    394
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    190
    +0.16
    0.06
    1987
    +0.14
    0.06
    46
    +0.10
    0.05
    Negative Logits
    <bos>
    -1.48
     intersper
    -1.18
     shenan
    -1.06
     underval
    -1.02
     vainly
    -1.01
     endeavored
    -0.98
     strove
    -0.98
     renounced
    -0.97
     impelled
    -0.96
     faggot
    -0.94
    POSITIVE LOGITS
     alkoh
    1.35
     plak
    1.19
     optik
    1.18
     kosme
    1.17
     Kategor
    1.15
     keramik
    1.13
     silikon
    1.13
     kran
    1.11
     maksi
    1.11
     kafe
    1.06
    Activations Density 0.279%

    No Known Activations