© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13820
    Prev
    Next
    INDEX
    Explanations

    references to technological advancements and innovations

    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
    1577
    +0.27
    0.9%
    964
    +0.15
    0.5%
    776
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    776
    +0.27
    0.18
    198
    +0.15
    0.15
    939
    +0.12
    0.17
    Negative Logits
    <bos>
    -1.13
     peines
    -0.84
     Ottobre
    -0.82
     Luglio
    -0.74
     Giugno
    -0.74
     quæ
    -0.73
     GRATU
    -0.72
     bandai
    -0.72
     sappi
    -0.71
     Secrétaire
    -0.71
    POSITIVE LOGITS
     recent
    0.69
     lately
    0.61
     recently
    0.59
     dozens
    0.58
     examples
    0.57
     countless
    0.56
     anecdotal
    0.55
     innumerable
    0.54
    Recently
    0.54
    recent
    0.54
    Activations Density 8.392%

    No Known Activations