© 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. 6432
    Prev
    Next
    INDEX
    Explanations

    references to the TV show "Star Trek."

    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
    871
    +0.14
    0.5%
    1573
    +0.13
    0.5%
    1141
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1307
    +0.14
    0.02
    1573
    +0.13
    0.02
    86
    +0.10
    0.02
    Negative Logits
     intptr
    -0.59
    ValueStyle
    -0.59
     ExecuteAsync
    -0.58
     OMITBAD
    -0.58
    IVEREF
    -0.56
     насељу
    -0.56
    SequentialGroup
    -0.55
    DockStyle
    -0.54
    windowFixed
    -0.54
    ValueGeneration
    -0.54
    POSITIVE LOGITS
     Trek
    1.03
     Traité
    0.92
     Docteur
    0.85
     milf
    0.85
     Messieurs
    0.83
    Trek
    0.81
     Ministre
    0.78
     Souha
    0.77
     Mémoires
    0.77
     Trekking
    0.76
    Activations Density 0.129%

    No Known Activations