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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 552
    Prev
    Next
    INDEX
    Explanations

    comment indicators used in coding or documentation

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

    code comment starters

    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
    XmlAccessType
    -0.49
     Erfüllung
    -0.42
    Président
    -0.41
     Bewußt
    -0.40
    moveToFirst
    -0.39
    GOTREF
    -0.39
     claramente
    -0.36
    FieldDescriptor
    -0.36
    DockStyle
    -0.36
     respiración
    -0.36
    POSITIVE LOGITS
    /*
    0.88
    //
    0.74
    /*
    0.71
     дописавши
    0.69
    ✨:
    0.62
    /**
    0.59
     /*
    0.56
    +/*
    0.55
     <<<<<<<<<<<<<<
    0.54
    RTLD
    0.53
    Activations Density 0.003%

    No Known Activations