© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 46713
    Prev
    Next
    INDEX
    Explanations

    specific biochemical compounds, particularly those related to viruses and their classifications

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

    list of specific items

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    PendingIntent
    -0.29
    クタイ
    -0.25
    EditorGUILayout
    -0.24
     http
    -0.24
     CreateTagHelper
    -0.24
     convenable
    -0.24
     however
    -0.23
     bzw
    -0.23
    的发
    -0.23
     either
    -0.23
    POSITIVE LOGITS
     Administrativna
    0.68
     NSCoder
    0.66
    Datuak
    0.65
    SourceChecksum
    0.65
    IsContent
    0.64
    ьаж
    0.64
    +#+#
    0.60
    TypedDataSet
    0.59
     protoimpl
    0.59
    הערות
    0.59
    Activations Density 0.056%

    No Known Activations