Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 31-GEMMASCOPE-RES-16K
    6. 16250
    Prev
    Next
    INDEX
    Explanations

    procedures and conditions related to legal and administrative processes, particularly in contexts of identity verification and obligations

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

    Japanese verbs

    np_acts-logits-general · gemini-2.0-flash

    actions leading to a consequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    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
    われました
    -0.56
    していきます
    -0.54
    してくれます
    -0.53
    われています
    -0.50
    られています
    -0.49
    かれています
    -0.49
    новниш
    -0.49
    いています
    -0.48
    されていました
    -0.47
    っていきます
    -0.47
    POSITIVE LOGITS
     done
    0.56
     TAMBÉM
    0.55
     viewDidLoad
    0.49
    íqu
    0.45
     Hon
    0.43
    done
    0.43
     did
    0.43
    orElseThrow
    0.42
     Honig
    0.42
    ulated
    0.41
    Activations Density 0.036%

    No Known Activations