© 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. 3520
    Prev
    Next
    INDEX
    Explanations

    technical specifications and terms related to electronic devices

    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
    1438
    +0.11
    0.3%
    1978
    +0.10
    0.3%
    453
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.11
    0.01
    1241
    +0.10
    0.03
    1919
    +0.09
    0.03
    Negative Logits
     fta
    -1.69
     napoli
    -1.65
     milf
    -1.62
     mef
    -1.61
     wien
    -1.61
     squa
    -1.60
     ftu
    -1.59
     milano
    -1.58
     aen
    -1.56
     eiffel
    -1.54
    POSITIVE LOGITS
     has
    0.87
     will
    0.82
     does
    0.81
     did
    0.78
     may
    0.77
     can
    0.76
     cannot
    0.76
     took
    0.76
     had
    0.74
     should
    0.74
    Activations Density 0.130%

    No Known Activations