© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 7097
    Prev
    Next
    INDEX
    Explanations

    references to spoiler warnings and related concerns

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

    Warnings about spoilers

    np_acts-logits-general · gemini-2.0-flash

    warning about spoilers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithIOException
    -0.56
    MessageTagHelper
    -0.53
    enumii
    -0.51
    Datuak
    -0.48
    Lähteet
    -0.45
     NSCoder
    -0.45
     مشين
    -0.43
    stonia
    -0.42
    umbersome
    -0.42
    indrical
    -0.41
    POSITIVE LOGITS
     spoilers
    1.27
     spoiler
    1.22
    Spoiler
    1.14
    spoiler
    1.13
    Spoilers
    1.11
     Spoiler
    1.08
     SPOILERS
    1.03
     Spoilers
    1.02
    SPOILER
    0.97
     SPOILER
    0.94
    Activations Density 0.217%

    No Known Activations