© 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
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 3843
    Prev
    Next
    INDEX
    Explanations

    references to unfamiliar or lesser-known individuals and entities

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

    "Never heard of" or unfamiliarity

    np_acts-logits-general · gemini-2.0-flash

    familiarity or lack thereof

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArgumentParser
    -0.45
    dataclass
    -0.44
    brainly
    -0.38
    +#+#
    -0.37
    
    -0.37
    providedIn
    -0.35
     Pristupljeno
    -0.35
    UnusedPrivate
    -0.33
    CESO
    -0.31
    makeText
    -0.30
    POSITIVE LOGITS
     familiar
    1.62
     familiarity
    1.51
    familiar
    1.49
    Familiar
    1.35
     Familiar
    1.30
     acquainted
    1.15
     unfamiliar
    1.12
     familiarize
    1.09
     знако
    1.08
    famili
    1.06
    Activations Density 0.309%

    No Known Activations