© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14848
    Prev
    Next
    INDEX
    Explanations

    code snippets related to software frameworks and configurations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1097
    +0.10
    0.3%
    1407
    +0.10
    0.3%
    499
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.10
    0.00
    1871
    +0.10
    0.03
    453
    +0.09
    0.03
    Negative Logits
     ujedno
    -0.71
     MediatR
    -0.67
    mistak
    -0.66
     cytoplas
    -0.59
     McLaugh
    -0.58
     Stateful
    -0.54
     plak
    -0.54
    thinkable
    -0.53
    relenting
    -0.53
     Rumania
    -0.53
    POSITIVE LOGITS
     obiet
    0.67
    JS
    0.66
     dimenti
    0.63
     JS
    0.61
    js
    0.60
     JavaScript
    0.59
     Javascript
    0.57
     pantal
    0.57
     😭😭
    0.56
     vogli
    0.56
    Activations Density 0.164%

    No Known Activations