© 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. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 3408
    Prev
    Next
    INDEX
    Explanations

    phrases related to broader contexts or perspectives

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1264
    +0.09
    0.3%
    872
    +0.09
    0.2%
    1919
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1264
    +0.09
    0.03
    1923
    +0.09
    0.04
    1903
    +0.07
    0.03
    Negative Logits
     reluct
    -1.27
     disagre
    -1.26
     maneu
    -1.24
     intersper
    -1.24
     accla
    -1.23
     Keny
    -1.22
     Juf
    -1.21
     depic
    -1.19
     emphat
    -1.18
     guarante
    -1.17
    POSITIVE LOGITS
     as
    0.60
     որ
    0.58
     pyplot
    0.58
     perspective
    0.55
     view
    0.55
     viewed
    0.55
    viewBox
    0.54
     jako
    0.53
    デューサー
    0.53
    viewType
    0.53
    Activations Density 0.260%

    No Known Activations