© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 20150
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "abstract" and references to figures, captions, and mathematical operations

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

    abstract introductions

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     defaultstate
    -0.67
    ագրություններ
    -0.54
     ostavi
    -0.49
     تعدى
    -0.49
    MLLoader
    -0.48
    EndContext
    -0.43
     FetchType
    -0.42
    ">//
    -0.41
     оригіналу
    -0.40
    oshiba
    -0.39
    POSITIVE LOGITS
    abstract
    1.48
     abstract
    1.01
     ABSTRACT
    0.98
    Abstract
    0.97
     Abstract
    0.96
    ABSTRACT
    0.96
     abstracta
    0.74
     abstracts
    0.74
    abstra
    0.74
     abstra
    0.74
    Activations Density 0.003%

    No Known Activations