© 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. 2766
    Prev
    Next
    INDEX
    Explanations

    references to programming languages and software development

    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
    +0.30
    1.3%
    764
    +0.28
    1.3%
    1842
    +0.19
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    764
    +0.30
    0.02
    1978
    +0.28
    0.04
    1042
    +0.19
    0.02
    Negative Logits
    <bos>
    -3.07
    —
    -0.98
    <em>
    -0.95
    <u>
    -0.93
    –
    -0.92
    “
    -0.92
    Referències
    -0.92
    <i>
    -0.92
    Panamoan
    -0.91
    <strong>
    -0.91
    POSITIVE LOGITS
     shenan
    3.44
     reluct
    3.28
     impra
    3.20
     disagre
    3.13
     unspeak
    3.05
     maneu
    3.04
     apprehen
    3.02
     affor
    3.02
     philanth
    2.98
     indestru
    2.97
    Activations Density 0.285%

    No Known Activations