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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11378
    Prev
    Next
    INDEX
    Explanations

    references to in-game elements and characters in a fantasy video game

    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
    2015
    +0.11
    0.3%
    394
    +0.10
    0.3%
    946
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    422
    +0.11
    0.04
    394
    +0.10
    0.05
    736
    +0.10
    0.07
    Negative Logits
     alkoh
    -1.04
     kosme
    -0.95
     makro
    -0.95
     akut
    -0.94
     fré
    -0.91
     asfal
    -0.91
     silikon
    -0.91
     kön
    -0.90
     optik
    -0.90
     soigne
    -0.90
    POSITIVE LOGITS
     despotism
    0.83
     belliger
    0.65
     benevolence
    0.59
     Fascism
    0.58
     benevolent
    0.57
     philosophic
    0.56
     subserv
    0.55
     genoc
    0.55
     communists
    0.55
     venge
    0.54
    Activations Density 0.650%

    No Known Activations