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. 15385
    Prev
    Next
    INDEX
    Explanations

    instances of numbers and technical terms related to a structured text or study

    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
    +0.19
    0.6%
    1870
    +0.14
    0.4%
    2034
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.19
    0.04
    1510
    +0.14
    0.03
    1274
    +0.11
    0.03
    Negative Logits
     sappi
    -1.32
     scopri
    -1.06
     migli
    -0.94
     Augu
    -0.92
     PLW
    -0.91
     abbra
    -0.91
     rispond
    -0.91
     dichi
    -0.90
     affez
    -0.90
     dora
    -0.90
    POSITIVE LOGITS
     and
    0.82
     or
    0.76
     и
    0.70
     và
    0.69
    以及
    0.67
     или
    0.66
    bibnamefont
    0.64
     versus
    0.63
    和
    0.63
    และ
    0.62
    Activations Density 0.216%

    No Known Activations