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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6385
    Prev
    Next
    INDEX
    Explanations

    references to software programming concepts and error handling

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

    C/C++ code and standard libraries

    np_acts-logits-general · gemini-2.0-flash

    C++ standard library includes and system calls

    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
    mtliche
    -0.47
     يتيمه
    -0.42
    sigkeit
    -0.36
     <>",
    -0.36
     Sá
    -0.35
     hotspot
    -0.34
     huk
    -0.32
    près
    -0.32
    ázaro
    -0.32
    typedef
    -0.32
    POSITIVE LOGITS
     resourceCulture
    0.61
    ########.
    0.60
    EDEFAULT
    0.57
    ismet
    0.54
     JpaRepository
    0.53
    iostream
    0.53
    IsPostBack
    0.52
    stdc
    0.52
    JspWriter
    0.51
     SwitchCompat
    0.50
    Activations Density 0.617%

    No Known Activations