© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2620
    Prev
    Next
    INDEX
    Explanations

    references to endangered species and their conservation status

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

    information about species, particularly endangered or endemic species, with a focus on detailed scientific descriptions and conservation status.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.60
     تانيه
    -0.59
     برانيه
    -0.58
     ProtoMessage
    -0.58
     noDo
    -0.56
    ftagPool
    -0.55
     يتيمه
    -0.54
    sidemargin
    -0.54
    ंदीखरीदारी
    -0.53
    Autoritní
    -0.52
    POSITIVE LOGITS
     endangered
    0.56
     threatened
    0.56
     Threatened
    0.52
     menac
    0.47
     threat
    0.44
     Endangered
    0.43
    threat
    0.43
     threatens
    0.42
     extinction
    0.42
     threaten
    0.41
    Activations Density 0.130%

    No Known Activations