© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 125088
    Prev
    Next
    INDEX
    Explanations

    code-related references and imports in programming context, particularly focusing on Python packages and commands

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

    commands and execution

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    elasticsearch
    -0.47
     Choisissez
    -0.40
    ClickListener
    -0.39
     przechowy
    -0.39
    INCREF
    -0.38
    Viited
    -0.38
     loisirs
    -0.37
     giver
    -0.37
    mobileqq
    -0.36
    сього
    -0.35
    POSITIVE LOGITS
     subprocess
    2.42
    subprocess
    1.67
    toThrow
    0.60
     subroutine
    0.60
     CURIAM
    0.60
    InputTagHelper
    0.60
     المعيارى
    0.59
    ftagPool
    0.57
    出版年
    0.56
     argparse
    0.56
    Activations Density 0.001%

    No Known Activations