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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 14755
    Prev
    Next
    INDEX
    Explanations

    phrases describing methods or manners of doing things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    JspWriter
    -0.41
     presidencial
    -0.40
     déb
    -0.38
    usercontent
    -0.36
     nonUne
    -0.36
    vole
    -0.35
    Existence
    -0.35
    included
    -0.35
    venser
    -0.35
     Presidencia
    -0.34
    POSITIVE LOGITS
     manner
    0.75
     maniera
    0.58
    manner
    0.57
     CreateTagHelper
    0.57
     ways
    0.57
     maneras
    0.56
     manières
    0.56
     way
    0.54
     manière
    0.54
     Manner
    0.54
    Activations Density 0.471%

    No Known Activations