© 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. 11-GEMMASCOPE-RES-16K
    6. 8897
    Prev
    Next
    INDEX
    Explanations

    syntax elements related to conditional statements and optional parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     برانيه
    -0.46
    ItemBackground
    -0.41
    richTextPanel
    -0.38
    ⟬
    -0.37
     CreateTagHelper
    -0.37
    protoimpl
    -0.37
    BagLayout
    -0.35
    AndEndTag
    -0.35
    reservations
    -0.35
     <<<<<<<<<<<<<<
    -0.34
    POSITIVE LOGITS
    orElseThrow
    0.65
    assertNotNull
    0.62
    Nonnull
    0.60
     Wikimedijinoj
    0.59
    requireNonNull
    0.54
    ElementException
    0.54
    tableFuture
    0.53
    Nullable
    0.52
    toBeDefined
    0.51
    NonNull
    0.48
    Activations Density 0.281%

    No Known Activations