© 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
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 3406
    Prev
    Next
    INDEX
    Explanations

    structured academic contexts and roles

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

    academic and professional credentials or affiliations, particularly student and degree status.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    withIdentifier
    -0.46
    fjspx
    -0.42
    ViewFeatures
    -0.39
    PYX
    -0.37
    WithIOException
    -0.37
    ioutil
    -0.36
    URLException
    -0.36
    iNdEx
    -0.36
    tagHelperRunner
    -0.36
     تكبرها
    -0.35
    POSITIVE LOGITS
     students
    2.52
     student
    2.41
     Students
    2.13
    students
    2.11
    student
    2.03
    Students
    2.03
     STUDENTS
    1.95
     Student
    1.94
    Student
    1.90
     estudiantes
    1.87
    Activations Density 0.318%

    No Known Activations