© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 8780
    Prev
    Next
    INDEX
    Explanations

    questions and uncertainties regarding tasks or problems

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

    "What am I [negative action]?"

    np_acts-logits-general · gemini-2.0-flash

    questions about errors or missing things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     souff
    -0.49
     Partagez
    -0.47
    Winning
    -0.46
    PyExc
    -0.44
    OuterClass
    -0.44
     Winning
    -0.42
     bestehen
    -0.42
    ymce
    -0.41
    niet
    -0.40
     Maiden
    -0.40
    POSITIVE LOGITS
     missed
    1.48
     Missed
    1.24
     incorrectly
    1.22
    missed
    1.20
     wrongly
    1.19
     miss
    1.18
     forgot
    1.16
     mistakenly
    1.15
     mis
    1.14
    Missed
    1.13
    Activations Density 0.404%

    No Known Activations