© 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. 9-GEMMASCOPE-RES-16K
    6. 8921
    Prev
    Next
    INDEX
    Explanations

    elements related to evidence and witness testimony in a legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    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
    canestro
    -0.40
    VIAF
    -0.35
    AdapterView
    -0.33
     NUT
    -0.33
     Wild
    -0.33
     Reg
    -0.33
     bedrijven
    -0.32
     handleMessage
    -0.32
     wild
    -0.32
     Bre
    -0.32
    POSITIVE LOGITS
     forensic
    0.85
     Forensic
    0.85
    Forensic
    0.84
    nsics
    0.77
    +:+
    0.68
    nsic
    0.58
    labus
    0.55
     OMITBAD
    0.53
     kasarigan
    0.53
    Demografie
    0.52
    Activations Density 1.072%

    No Known Activations