Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 448
    Prev
    Next
    INDEX
    Explanations

    references to actions or plans for the future

    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
    674
    +0.16
    0.6%
    1325
    +0.13
    0.4%
    1053
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1053
    +0.16
    0.06
    1325
    +0.13
    0.05
    404
    +0.11
    0.05
    Negative Logits
     Sinal
    -0.72
     thuy
    -0.58
     Cár
    -0.58
     lele
    -0.56
     Minang
    -0.56
     Mejía
    -0.53
     Practically
    -0.53
     blackness
    -0.52
     Arro
    -0.52
     EEU
    -0.52
    POSITIVE LOGITS
     going
    1.00
    going
    0.93
     GOING
    0.91
     Going
    0.84
    Going
    0.80
    GOING
    0.78
     gonna
    0.76
     goin
    0.69
    ngoing
    0.58
     go
    0.58
    Activations Density 0.083%

    No Known Activations