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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 6264
    Prev
    Next
    INDEX
    Explanations

    code and syntax structures typical in programming languages

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

    Code snippets using file operations

    np_acts-logits-general · gemini-2.0-flash

    programming keywords and non-english words

    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
    abstractmethod
    -0.65
     onPostExecute
    -0.63
     ddelweddau
    -0.54
     <<<<<<<<<<<<<<
    -0.53
    PYX
    -0.51
    SerializeField
    -0.50
    IBOutlet
    -0.50
    MigrationBuilder
    -0.49
    strptime
    -0.49
     deſt
    -0.49
    POSITIVE LOGITS
     Савезне
    0.58
     psicológico
    0.38
     görül
    0.37
     klachten
    0.36
     paraître
    0.35
     económica
    0.35
     örgü
    0.35
    IUrlHelper
    0.34
     psicológica
    0.33
    Combine
    0.33
    Activations Density 0.087%

    No Known Activations