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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 7127
    Prev
    Next
    INDEX
    Explanations

    references to the letter "D" in various contexts, potentially indicating its importance in a scientific or technical discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    greSQL
    -0.59
    latego
    -0.59
    ाउनलोड
    -0.52
    ι
    -0.51
    ЛЯ
    -0.51
    withstanding
    -0.50
    umbledore
    -0.49
    PAIGN
    -0.49
    SequentialGroup
    -0.49
     ProtoMessage
    -0.49
    POSITIVE LOGITS
    省市镇
    0.45
    ónde
    0.44
    原始内容存档于
    0.42
    zień
    0.40
    SB
    0.40
    SV
    0.39
    imens
    0.39
    ział
    0.38
    imana
    0.37
    ANGER
    0.37
    Activations Density 0.215%

    No Known Activations