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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3118
    Prev
    Next
    INDEX
    Explanations

    SQL commands and syntax

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

    SQL code snippets or queries

    np_acts-logits-general · gemini-2.0-flash

    SQL commands like SET and SELECT

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     gyhoeddwyd
    -0.45
    UnusedPrivate
    -0.44
    MigrationBuilder
    -0.42
     HasFactory
    -0.41
    <_>
    -0.39
    webElement
    -0.39
    FieldBuilder
    -0.38
    Ӕ
    -0.38
     EconPapers
    -0.37
     հղումներ
    -0.36
    POSITIVE LOGITS
    ParallelGroup
    0.73
    antMatchers
    0.70
    Portale
    0.59
    noinspection
    0.59
    orianCalendar
    0.58
    SuppressLint
    0.54
     +%
    0.51
    بوابة
    0.51
    Matchers
    0.49
    fjspx
    0.48
    Activations Density 0.195%

    No Known Activations