© 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. 22-GEMMASCOPE-RES-16K
    11. 12645
    Prev
    Next
    INDEX
    Explanations

    references to structured data representation and documentation

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

    Statements/lists introduced by "as follows" or "following"

    np_acts-logits-general · gemini-2.0-flash

    introduces lists following 'as'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lenker
    -0.58
    rboles
    -0.54
    دانشنامهٔ
    -0.52
    Somehow
    -0.52
     Somehow
    -0.52
    itisation
    -0.51
    ')['
    -0.51
    μως
    -0.50
    Portale
    -0.50
     tudom
    -0.50
    POSITIVE LOGITS
     following
    3.19
    following
    2.81
     Following
    2.40
    Following
    2.30
     FOLLOWING
    2.27
     siguientes
    2.25
     seguenti
    2.21
     siguiente
    2.14
     seguinte
    2.11
    以下
    2.07
    Activations Density 0.657%

    No Known Activations