© 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. 7550
    Prev
    Next
    INDEX
    Explanations

    adjectives that describe quality or attributes

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

    Adjective after indefinite article ("a" or "an")

    np_acts-logits-general · gemini-2.0-flash

    a followed by positive adjectives

    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
    Demografie
    -0.65
    antMatchers
    -0.60
    StoryboardSegue
    -0.57
    دانشنامهٔ
    -0.54
     pinulongan
    -0.54
    TypedDataSet
    -0.53
    Obrázky
    -0.53
    prefixer
    -0.53
    .*")]
    -0.52
    yntaxException
    -0.52
    POSITIVE LOGITS
     very
    0.65
     unique
    0.56
     highly
    0.56
     distinctly
    0.55
     truly
    0.54
     fairly
    0.52
     extremely
    0.50
     tremendous
    0.50
     decidedly
    0.49
     fantastic
    0.48
    Activations Density 0.436%

    No Known Activations