© 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 EvalsExportsinterp-engineNEWAPI 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. 15191
    Prev
    Next
    INDEX
    Explanations

    video game attributes and stats, such as movement speed and mana regeneration

    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
    1343
    +0.15
    0.4%
    856
    +0.13
    0.4%
    1870
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    536
    +0.15
    0.03
    764
    +0.13
    0.03
    1343
    +0.09
    0.03
    Negative Logits
    TestBed
    -0.66
    Todavía
    -0.64
    Varios
    -0.64
    Obrigada
    -0.63
    Será
    -0.61
    Hvor
    -0.61
    Obrigado
    -0.61
    Possui
    -0.60
    Muito
    -0.59
    está
    -0.59
    POSITIVE LOGITS
     ?...
    1.47
     !...
    1.43
     fluo
    1.41
     impra
    1.41
     cabrio
    1.39
     intermitt
    1.39
     suscep
    1.38
     embodi
    1.37
     vespa
    1.37
     strick
    1.37
    Activations Density 0.101%

    No Known Activations