© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 12148
    Prev
    Next
    INDEX
    Explanations

    discussions about sports matches and player strategies

    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
    1577
    +0.34
    1.2%
    381
    +0.21
    0.7%
    50
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2044
    +0.34
    0.18
    1959
    +0.21
    0.17
    1577
    +0.16
    0.17
    Negative Logits
     keramik
    -1.25
     magis
    -1.23
     alkoh
    -1.21
     monaster
    -1.20
     venuto
    -1.15
     ecclesias
    -1.13
     silikon
    -1.11
     nomine
    -1.11
     kompati
    -1.10
     kosme
    -1.10
    POSITIVE LOGITS
     anyway
    0.76
     also
    0.74
     however
    0.72
     anyways
    0.72
     prolly
    0.71
     definately
    0.68
     therefore
    0.66
     certainly
    0.66
     furthermore
    0.65
     anyhow
    0.65
    Activations Density 3.877%

    No Known Activations