© 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. 2-GEMMASCOPE-RES-16K
    11. 8097
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of "needle" and references to medical or procedural contexts involving its use

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.64
    ----</
    -0.55
    رشف
    -0.53
     unknownFields
    -0.48
    amate
    -0.47
    Sklici
    -0.47
     Fests
    -0.45
    Історія
    -0.45
     Westen
    -0.45
    ษา
    -0.44
    POSITIVE LOGITS
    ils
    0.59
     needles
    0.57
    Bass
    0.56
    Basin
    0.54
    ILS
    0.54
     Basin
    0.53
     Oriented
    0.53
     Bass
    0.53
    ide
    0.51
     needle
    0.51
    Activations Density 0.453%

    No Known Activations