© 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. 9-GEMMASCOPE-RES-131K
    6. 20183
    Prev
    Next
    INDEX
    Explanations

    syntax structures and control flow statements in programming code

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

    conditional programming statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageState
    -0.52
    setupUi
    -0.51
     linkovi
    -0.49
     referenties
    -0.48
    \{\\
    -0.47
    Enllaços
    -0.46
    AutoScaleMode
    -0.45
    SharedDtor
    -0.44
    MigrationBuilder
    -0.44
    новниш
    -0.44
    POSITIVE LOGITS
    												
    0.50
     Chwiliwch
    0.48
    																							
    0.46
    																						
    0.46
                                
    0.46
    														
    0.42
    																											
    0.42
    																			
    0.42
    FormUrlEncoded
    0.41
    															
    0.41
    Activations Density 0.075%

    No Known Activations