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
    4. Residual Stream - 16k
    5. 34-GEMMASCOPE-RES-16K
    6. 10869
    Prev
    Next
    INDEX
    Explanations

    relational phrases and expressions of personal connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArrowToggle
    -0.71
     Normdatei
    -0.64
    MessageTagHelper
    -0.63
     Audiodateien
    -0.62
     препратки
    -0.60
    XmlAccessType
    -0.57
     BoxFit
    -0.54
     المعيارى
    -0.54
    الحياه
    -0.54
     strconv
    -0.53
    POSITIVE LOGITS
     ours
    3.41
     theirs
    3.22
     yours
    3.13
     hers
    3.08
     mine
    3.02
     Ours
    2.67
    Ours
    2.55
    Mine
    2.47
     Yours
    2.42
     Mine
    2.38
    Activations Density 0.560%

    No Known Activations