© 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
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 19
    Prev
    Next
    INDEX
    Explanations

    references to hooks and related mechanisms or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    richTextPanel
    -0.42
    MemoryWarning
    -0.42
    nvarchar
    -0.36
     يتيمه
    -0.36
    /**
    -0.36
    SystemColors
    -0.36
    tagHelperRunner
    -0.35
    DateTimeFormat
    -0.35
    GEBURTS
    -0.34
    IsContent
    -0.34
    POSITIVE LOGITS
     Hook
    1.36
     hook
    1.33
    Hook
    1.29
     HOOK
    1.28
    hook
    1.16
     hooks
    1.14
     Hooks
    1.13
     hooked
    1.12
     hooking
    1.11
    HOOK
    1.08
    Activations Density 0.153%

    No Known Activations