© 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. 7261
    Prev
    Next
    INDEX
    Explanations

    mentions of physical contact or interaction

    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
    1482
    +0.19
    0.7%
    1350
    +0.12
    0.4%
    196
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1482
    +0.19
    0.04
    196
    +0.12
    0.02
    1350
    +0.12
    0.02
    Negative Logits
    ICU
    -0.47
     jard
    -0.46
     Buen
    -0.45
    logio
    -0.44
     BASF
    -0.44
    pagni
    -0.44
     Girolamo
    -0.44
     Bienen
    -0.44
     hib
    -0.44
     Nal
    -0.43
    POSITIVE LOGITS
     touch
    1.43
     TOUCH
    1.30
    touch
    1.30
     Touch
    1.29
     touched
    1.21
     touches
    1.21
    Touch
    1.19
    TOUCH
    1.12
    touched
    1.11
     touching
    1.08
    Activations Density 0.091%

    No Known Activations