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. 15668
    Prev
    Next
    INDEX
    Explanations

    astronomical and space-related terms

    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
    50
    +0.23
    0.9%
    1177
    +0.20
    0.8%
    1741
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1177
    +0.23
    0.07
    678
    +0.20
    0.13
    1965
    +0.13
    0.09
    Negative Logits
    <bos>
    -1.17
    ertos
    -0.62
     simplifié
    -0.58
    WithMany
    -0.58
    databind
    -0.57
    .
    -0.57
    IANGLES
    -0.56
     Obrador
    -0.56
    떻
    -0.56
    principalColumn
    -0.56
    POSITIVE LOGITS
     wien
    1.88
     aen
    1.88
     mef
    1.84
     increa
    1.83
     emphat
    1.83
     inev
    1.81
     effe
    1.81
     Juf
    1.79
     reluct
    1.76
     disagre
    1.76
    Activations Density 2.334%

    No Known Activations