© 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. 13716
    Prev
    Next
    INDEX
    Explanations

    references to technology and technical details

    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
    1937
    +0.16
    0.7%
    1096
    +0.16
    0.7%
    1323
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1096
    +0.16
    0.03
    1323
    +0.16
    0.02
    1491
    +0.14
    0.02
    Negative Logits
    lanzen
    -0.52
    artamentos
    -0.48
     zvuky
    -0.46
    ganu
    -0.43
     piłkarz
    -0.42
    bolista
    -0.42
    lusst
    -0.42
    cookies
    -0.42
     tycker
    -0.41
    יצד
    -0.41
    POSITIVE LOGITS
     Ser
    1.18
    Ser
    1.09
     ser
    1.08
     SER
    1.03
     serials
    1.01
     sergio
    1.00
     Serial
    0.99
     serial
    0.94
     Sermons
    0.93
     exé
    0.92
    Activations Density 0.132%

    No Known Activations