© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 6485
    Prev
    Next
    INDEX
    Explanations

    segments of dialogue and courtroom exchanges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    帖最后由
    -0.59
     ujednoznacz
    -0.55
    OGND
    -0.52
    AndroidJUnit
    -0.49
    WriteTagHelper
    -0.49
     Normdatei
    -0.49
    ReusableCell
    -0.48
    هایت
    -0.45
     ſind
    -0.45
    CppMethod
    -0.45
    POSITIVE LOGITS
    >//
    0.49
    ագրություններ
    0.47
     berkata
    0.42
     says
    0.40
    hood
    0.39
    참고
    0.39
    ########.
    0.38
    COMMERCIAL
    0.37
    horizontalLayout
    0.36
    complexType
    0.36
    Activations Density 0.444%

    No Known Activations