© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 4772
    Prev
    Next
    INDEX
    Explanations

    statements of belief or opinion regarding human rights and well-being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igshid
    -0.69
    ("")]
    -0.65
    ContentAsync
    -0.59
    CloseOperation
    -0.58
    Spenden
    -0.55
    UnknownFieldSet
    -0.55
     CreateTagHelper
    -0.53
     hieß
    -0.53
    TagHelpers
    -0.53
     typelib
    -0.53
    POSITIVE LOGITS
     sufficient
    0.65
     suitable
    0.63
    suitable
    0.61
    sufficient
    0.59
     ✭✭
    0.58
     worth
    0.56
    worthy
    0.55
     sufficiently
    0.54
     appropriate
    0.53
     merit
    0.53
    Activations Density 0.436%

    No Known Activations