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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 2536
    Prev
    Next
    INDEX
    Explanations

    words related to thinking, discussing, or describing

    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
    +0.16
    0.5%
    1971
    +0.09
    0.3%
    1042
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2025
    +0.16
    0.04
    111
    +0.09
    0.02
    1372
    +0.09
    0.04
    Negative Logits
     strick
    -1.30
     volunte
    -1.28
     affor
    -1.27
     increa
    -1.26
     maneu
    -1.24
     snoopy
    -1.23
     unlaw
    -1.23
     disagre
    -1.21
     impra
    -1.20
     Daven
    -1.19
    POSITIVE LOGITS
    <bos>
    0.98
     it
    0.78
    Personensuche
    0.70
     ello
    0.64
     nó
    0.63
     дописавши
    0.63
     estekak
    0.60
     Paglinawan
    0.59
    躇
    0.59
     them
    0.57
    Activations Density 0.362%

    No Known Activations