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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 5832
    Prev
    Next
    INDEX
    Explanations

    terms related to probation and offender management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "]();
    -0.43
     [*]
    -0.42
     تانيه
    -0.36
    sumi
    -0.36
     يتيمه
    -0.36
     przeds
    -0.36
    )$-
    -0.36
    SafeMath
    -0.35
    SEMICOLON
    -0.35
     zbior
    -0.35
    POSITIVE LOGITS
     rehabilitation
    0.69
     rehabilit
    0.64
     rehabilitate
    0.63
     Rehabilitation
    0.61
     rehab
    0.59
     unknownFields
    0.56
     Rehab
    0.56
     Efq
    0.52
     parole
    0.51
     vocational
    0.51
    Activations Density 0.559%

    No Known Activations