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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 31-GEMMASCOPE-RES-16K
    6. 9344
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to version control systems

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

    technical terms and keywords related to version control systems and software development tools.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    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
    :✨
    -0.48
    +#+
    -0.45
    +#+#
    -0.44
    Personendaten
    -0.44
    省市镇
    -0.44
     cows
    -0.40
    يميديا
    -0.38
     Zust
    -0.37
     бри
    -0.37
    dolu
    -0.36
    POSITIVE LOGITS
    SVN
    0.58
    svn
    0.58
     svn
    0.55
     SVN
    0.47
    存于互联网档案馆
    0.45
    isContained
    0.42
    رشف
    0.42
    OOTDTY
    0.41
     locking
    0.41
     ComVisible
    0.40
    Activations Density 0.364%

    No Known Activations