© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 1904
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to categorization and classification

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

    preceding "different", "diverse", or "varied"

    np_acts-logits-general · gemini-2.0-flash

    different styles or terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sidemargin
    -0.56
    Vidite
    -0.54
     betweenstory
    -0.54
    giques
    -0.53
    ombies
    -0.53
     Italijanski
    -0.53
    PhysRevLett
    -0.52
    emang
    -0.52
    ########.
    -0.51
    thunk
    -0.51
    POSITIVE LOGITS
     varied
    1.64
     diverse
    1.58
     different
    1.48
     variety
    1.42
    diverse
    1.41
     varying
    1.40
     diversity
    1.39
     Different
    1.30
    Different
    1.29
    different
    1.29
    Activations Density 0.890%

    No Known Activations