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. 22-GEMMASCOPE-RES-16K
    6. 10253
    Prev
    Next
    INDEX
    Explanations

    identifiers such as IDs, roles, and company names related to user, product, and session data

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

    Code snippets with properties

    np_acts-logits-general · gemini-2.0-flash

    session ID, item code, resource origin

    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
    Id
    -1.51
    nonatomic
    -0.63
     виправивши
    -0.60
     Id
    -0.58
    Name
    -0.53
    __*/
    -0.51
    hassee
    -0.50
     protoimpl
    -0.50
    じゃあ
    -0.49
     Таким
    -0.49
    POSITIVE LOGITS
     CreateTagHelper
    0.65
    Came
    0.53
     yourselves
    0.53
    dann
    0.52
    york
    0.51
    Followed
    0.51
    FontOfSize
    0.50
    elemField
    0.50
     cdti
    0.50
     Bho
    0.50
    Activations Density 0.129%

    No Known Activations