© 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. 5137
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "Abstract" in various contexts, particularly within programming or class hierarchy references

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

    abstract followed by classifier

    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
     SqlConnection
    -0.39
     imagePath
    -0.37
    ConstraintSet
    -0.36
    paravant
    -0.36
    URLException
    -0.35
     برانيه
    -0.34
    ñores
    -0.34
    WriteBarrier
    -0.34
    bamos
    -0.33
     használat
    -0.33
    POSITIVE LOGITS
     Abstract
    2.44
    Abstract
    1.94
     ABSTRACT
    1.59
     abstract
    1.50
    abstract
    1.46
     Abstracts
    1.30
    ABSTRACT
    1.27
     abstracts
    1.22
    Abstracts
    1.20
     Abstr
    1.16
    Activations Density 0.001%

    No Known Activations