© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 5241
    Prev
    Next
    INDEX
    Explanations

    mentions of marine or aquatic creatures, particularly cephalopods and gastropods

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

    Squid, slugs, snails, and octopus

    np_acts-logits-general · gemini-2.0-flash

    marine invertebrates

    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
    éroport
    -0.51
     clavic
    -0.51
    Crack
    -0.49
    jsonwebtoken
    -0.49
    unsaturated
    -0.48
     resourceCulture
    -0.47
    diamonds
    -0.47
    isRequired
    -0.47
    crack
    -0.46
    Cof
    -0.46
    POSITIVE LOGITS
     octopus
    0.71
     Octopus
    0.62
     squid
    0.60
     فريبيس
    0.56
    Octopus
    0.52
     snail
    0.50
     Squid
    0.50
    octopus
    0.48
     snails
    0.45
    イカ
    0.42
    Activations Density 0.406%

    No Known Activations