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
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 119
    Prev
    Next
    INDEX
    Explanations

    technical error messages related to software components and system operations

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

    error-related logging and debug statements in programming code.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.45
    TagNumber
    -0.44
     CreateTagHelper
    -0.43
    NameInMap
    -0.42
    __':
    
    -0.41
     fortæ
    -0.40
    VersionUID
    -0.40
    Atsauces
    -0.39
     dAtA
    -0.38
     prieten
    -0.38
    POSITIVE LOGITS
    BufferException
    0.59
    TintMode
    0.43
    发表于
    0.43
    destroyAll
    0.42
    ナル
    0.41
     viz
    0.41
    parseFrom
    0.40
     gonna
    0.39
    новништво
    0.39
     VP
    0.39
    Activations Density 0.243%

    No Known Activations