© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 479
    Prev
    Next
    INDEX
    Explanations

    instances of warranty and return policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "replacement" or "refund" following certain words

    np_acts-logits-general · gemini-2.0-flash

    return, replacement, or refund

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    passion
    -0.38
    Arm
    -0.36
    tences
    -0.35
    artan
    -0.35
    Envelope
    -0.35
    ANCES
    -0.34
    Workspace
    -0.33
     Sadd
    -0.33
     passion
    -0.33
     ensembles
    -0.32
    POSITIVE LOGITS
    GraphicsUnit
    0.69
    RenderAtEndOf
    0.66
     Италијани
    0.64
    OGND
    0.62
    AddTagHelper
    0.59
    GEBURTSDATUM
    0.58
     يتيمه
    0.56
     noDo
    0.55
    DebuggerNonUser
    0.55
    IsContent
    0.55
    Activations Density 0.085%

    No Known Activations