© 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. 121313
    Prev
    Next
    INDEX
    Explanations

    symbols and syntax elements commonly used in programming and code to represent operations or outputs

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

    string and arithmetic concatenation

    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
    :✨
    -0.64
    ]")]
    -0.63
     firebaseConfig
    -0.59
    +#+#
    -0.56
    fjspx
    -0.56
    RTDA
    -0.56
    };*/
    -0.55
     CreateTagHelper
    -0.52
    ="#"><
    -0.51
    )"),
    -0.51
    POSITIVE LOGITS
    IndentedString
    0.56
     pères
    0.44
    MigrationBuilder
    0.39
     defaultstate
    0.38
     numériques
    0.36
    rededor
    0.35
     chrétiens
    0.34
     tatouage
    0.34
    specialchars
    0.34
     maquiagem
    0.34
    Activations Density 0.005%

    No Known Activations