© 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. 9-GEMMASCOPE-RES-16K
    11. 7075
    Prev
    Next
    INDEX
    Explanations

    references to languages and locations, particularly those associated with Papua New Guinea and programming concepts related to Ember.js

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

    Geographic locations (Guinea, Namibia)

    np_acts-logits-general · gemini-2.0-flash

    countries and application routes

    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
    glVertex
    -0.41
    webtoken
    -0.40
    FieldBuilder
    -0.40
    omorphism
    -0.39
     kasarigan
    -0.39
    ioutil
    -0.39
    UnsafeEnabled
    -0.38
    arikat
    -0.38
    NUMX
    -0.38
     оба
    -0.38
    POSITIVE LOGITS
    OGND
    0.48
     Nebraska
    0.48
     Namib
    0.47
     Namibia
    0.46
    Namibia
    0.43
    ember
    0.42
    Nebraska
    0.41
    styleType
    0.41
    TagHelper
    0.40
     PyQt
    0.40
    Activations Density 0.308%

    No Known Activations