© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 9032
    Prev
    Next
    INDEX
    Explanations

    conditional phrases or scenarios involving medical or life choices

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

    "...in case of" or "event of"

    np_acts-logits-general · gemini-2.0-flash

    introducing conditional situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.39
     vivant
    -0.28
     esprits
    -0.28
     put
    -0.28
    cuerdo
    -0.28
     puissiez
    -0.27
     nomme
    -0.26
     judiciaire
    -0.26
     fotografia
    -0.26
     derniers
    -0.26
    POSITIVE LOGITS
     autorytatywna
    0.88
    AndEndTag
    0.85
    OGND
    0.76
    ConstraintMaker
    0.74
    +#+#
    0.72
    DockStyle
    0.68
    #
    0.66
    ArgumentParser
    0.66
     الحره
    0.63
    enumii
    0.62
    Activations Density 0.553%

    No Known Activations