© 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. 7034
    Prev
    Next
    INDEX
    Explanations

    phrases related to the act of using something

    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
    32
    +0.14
    0.5%
    662
    +0.13
    0.4%
    1124
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1124
    +0.14
    0.06
    1993
    +0.13
    0.06
    32
    +0.13
    0.05
    Negative Logits
    stdarg
    -0.57
    mpions
    -0.48
    mberto
    -0.48
    stddef
    -0.45
     Gallimard
    -0.45
    quarelle
    -0.45
    idelberg
    -0.44
     terrorismo
    -0.44
    acherous
    -0.44
     basan
    -0.43
    POSITIVE LOGITS
     use
    0.86
     Use
    0.85
     USE
    0.84
    use
    0.82
    Use
    0.81
     Uses
    0.81
    setUse
    0.79
    USE
    0.78
     uses
    0.73
     usage
    0.73
    Activations Density 0.195%

    No Known Activations