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. 8426
    Prev
    Next
    INDEX
    Explanations

    timestamps and textual excerpts from online conversations

    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
    1150
    +0.16
    0.5%
    1343
    +0.15
    0.5%
    906
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.16
    0.04
    1429
    +0.15
    0.04
    1431
    +0.10
    0.04
    Negative Logits
     surpl
    -0.69
     redé
    -0.68
     renou
    -0.67
     simplif
    -0.65
     doubl
    -0.57
     Sigue
    -0.55
     hairc
    -0.52
     plonge
    -0.52
     Haci
    -0.52
     Estar
    -0.52
    POSITIVE LOGITS
     ambientale
    0.48
    orded
    0.46
     Paglinawan
    0.45
     sogget
    0.44
    stination
    0.44
    .$_
    0.44
    ਾਨ
    0.44
     TimeUnit
    0.44
     worin
    0.43
    horesis
    0.43
    Activations Density 0.121%

    No Known Activations