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-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 1154
    Prev
    Next
    INDEX
    Explanations

    verbs and actions related to installations and preparations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     were
    -0.75
     have
    -0.58
     are
    -0.54
     weren
    -0.54
     byli
    -0.53
     read
    -0.53
    were
    -0.53
     אלה
    -0.51
     الذين
    -0.50
     explore
    -0.50
    POSITIVE LOGITS
     wears
    1.13
     sends
    1.07
     celebrates
    1.06
     reaches
    1.05
     prepares
    1.05
     marries
    1.05
     connects
    1.05
     earns
    1.04
     learns
    1.02
     goes
    1.02
    Activations Density 1.053%

    No Known Activations