© 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. 31-GEMMASCOPE-RES-16K
    11. 8957
    Prev
    Next
    INDEX
    Explanations

    adjectives that express varying degrees of quality, including positive and negative attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    positive descriptive adjectives that convey approval or favorable qualities.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     otomatig
    -0.59
     sufficiently
    -0.58
    \{\\
    -0.57
     enough
    -0.57
    enough
    -0.54
     suffisamment
    -0.52
     sufficient
    -0.52
    Personendaten
    -0.52
     galore
    -0.52
     Enough
    -0.51
    POSITIVE LOGITS
     fubject
    0.54
    UrlResolution
    0.53
    AndEndTag
    0.53
     indeed
    0.51
    @[+][
    0.50
     ſta
    0.49
    OCCURRED
    0.47
     inderdaad
    0.46
     poffible
    0.46
     pleaſure
    0.45
    Activations Density 0.489%

    No Known Activations