© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10892
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to analytical techniques and molecular structures

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

    FTIR and infrared spectroscopy

    np_acts-logits-general · gemini-2.0-flash

    FTIR spectroscopy analysis

    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
     Ker
    -0.36
    jsii
    -0.36
     men
    -0.35
    таратура
    -0.34
     MEN
    -0.34
     Shell
    -0.34
    phazard
    -0.33
    ventud
    -0.33
    relation
    -0.32
     avis
    -0.32
    POSITIVE LOGITS
    TabIndex
    0.66
    FTIR
    0.63
    CDCl
    0.62
     infrared
    0.59
    contentLoaded
    0.58
     spectroscopy
    0.57
     Administrativna
    0.57
    ConstraintMaker
    0.57
    RegistryLite
    0.56
     FTIR
    0.56
    Activations Density 1.038%

    No Known Activations