© 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-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 7740
    Prev
    Next
    INDEX
    Explanations

    terms related to spatial orientation and layout, specifically horizontal and vertical alignments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    BeginContext
    -0.67
    DataBind
    -0.65
    amplific
    -0.64
     ClassNotFound
    -0.63
     Idd
    -0.60
    ]--;
    -0.60
    appré
    -0.59
     wiesz
    -0.58
    strains
    -0.57
     ['./
    -0.56
    POSITIVE LOGITS
     horizontal
    1.45
     horizontally
    1.41
     Horizontal
    1.41
    Horizontal
    1.40
     vertically
    1.26
    horizontal
    1.23
     vertical
    1.23
     horizont
    1.22
    Vertical
    1.21
     Vertical
    1.19
    Activations Density 0.099%

    No Known Activations