Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 73714
    Prev
    Next
    INDEX
    Explanations

    concepts related to adherence to treatment protocols in healthcare contexts

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

    Key terminology specific to a domain or subject area, often representing important concepts, entities, or characteristics within technical or professional texts.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     ويكيپيديا
    -0.56
    Personendaten
    -0.44
     ESPECIAL
    -0.44
    Aholisi
    -0.43
     COMPAN
    -0.42
     lenker
    -0.42
    AddTagHelper
    -0.42
     and
    -0.42
    uxxxx
    -0.41
    PostInfinity
    -0.40
    POSITIVE LOGITS
    enumii
    0.50
    UserScript
    0.47
    Бахар
    0.46
    SharedDtor
    0.45
    ChildScrollView
    0.45
     مرئيه
    0.44
    fjspx
    0.42
    SequentialGroup
    0.42
     InputDecoration
    0.41
    RTLR
    0.41
    Activations Density 0.139%

    No Known Activations