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. 3050
    Prev
    Next
    INDEX
    Explanations

    instructions and information related to pet adoption

    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
    678
    +0.11
    0.3%
    961
    +0.08
    0.2%
    1490
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1786
    +0.11
    0.02
    1456
    +0.08
    0.03
    961
    +0.07
    0.02
    Negative Logits
    ()][
    -0.59
    Hochspringen
    -0.59
    enetrable
    -0.57
    vaného
    -0.56
    jspx
    -0.55
    ectoria
    -0.54
    anthene
    -0.54
    rativa
    -0.54
    ClassNotFound
    -0.53
    IActionResult
    -0.53
    POSITIVE LOGITS
     Hashtag
    1.45
     reluct
    1.45
     affor
    1.44
     increa
    1.44
     intersper
    1.43
     impra
    1.39
     encomp
    1.36
     strick
    1.36
     guarante
    1.36
     accla
    1.36
    Activations Density 0.197%

    No Known Activations