© 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. 12954
    Prev
    Next
    INDEX
    Explanations

    quantitative and financial information

    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
    2034
    +0.11
    0.3%
    1150
    +0.10
    0.3%
    1870
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1819
    +0.11
    0.07
    297
    +0.10
    0.06
    1171
    +0.10
    0.05
    Negative Logits
     mef
    -1.96
     wien
    -1.95
     „,
    -1.93
     fta
    -1.90
     squa
    -1.89
     secon
    -1.89
     emphat
    -1.85
     blos
    -1.83
     aen
    -1.82
     meis
    -1.81
    POSITIVE LOGITS
     per
    0.72
     with
    0.65
     plus
    0.64
     on
    0.62
    。
    0.62
     between
    0.62
    .
    0.62
     for
    0.61
     که
    0.60
    васто
    0.60
    Activations Density 0.467%

    No Known Activations